A new synergistic approach for monitoring wetlands using Sentinels -1 and 2 data with object-based machine learning algorithms

• Published in: Environmental modelling & software : with environment data news Vol. 104; pp. 40 - 54
• Main Authors: Whyte, Andrew, Ferentinos, Konstantinos P., Petropoulos, George P.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.06.2018; Elsevier Science Ltd
• Subjects: Algorithms; Array processors; Artificial intelligence; automation; Classification; data collection; Image analysis; Image processing; Image segmentation; Land cover; Land use; land use and land cover maps; Learning algorithms; Machine learning; Mapping; Moisture content; monitoring; Object-based classification; Random access memory; Random Forests; Sentinel-1; Sentinel-2; Statistical analysis; Support Vector Machines; Wetlands; Random Forests; Support Vector Machines; Sentinel-1; Object-based classification; Sentinel-2
• ISSN: 1364-8152; 1873-6726
• DOI: 10.1016/j.envsoft.2018.01.023

In this work the synergistic use of Sentinel-1 and 2 combined with the System for Automated Geoscientific Analyses (SAGA) Wetness Index in the content of land use/cover (LULC) mapping with emphasis in wetlands is evaluated. A further objective has been to develop a new Object-based Image Analysis (OBIA) approach for mapping wetland areas using Sentinel-1 and 2 data, where the latter is also tested against two popular machine learning algorithms (Support Vector Machines - SVMs and Random Forests - RFs). The highly vulnerable iSimangaliso Wetland Park was used as the study site. Results showed that two-part image segmentation could efficiently create object features across the study area. For both classification algorithms, an increase in overall accuracy was observed when the full synergistic combination of available datasets. A statistically significant difference in classification accuracy at all levels between SVMs and RFs was also reported, with the latter being up to 2.4% higher. SAGA wetness index showed promising ability to distinguish wetland environments, and in combination with Sentinel-1 and 2 synergies can successfully produce a land use and land cover classification in a location where both wetland and non-wetland classes exist. •Synergistic use of Sentinel-1 and 2 for wetland LULC mapping is evaluated.•A new OBIA method for LULC mapping with emphasis to mapping wetlands is proposed.•Advanced classification algorithms are implemented with Sentinel 1 & 2 data.•Findings highlight potential of Sentinel 1 & 2 synergies for improved wetland mapping.